Senior ML Deployment Engineer (Google Cloud Platform)

Introduction

As a Senior ML Deployment Engineer at our company, you will play a crucial role in deploying, benchmarking, and optimizing machine learning models for production on Google Cloud Platform (Google Cloud Platform). Your expertise in ML frameworks such as TensorFlow and PyTorch, along with your experience in performance tuning and quality testing, will be instrumental in ensuring the success of our ML deployment projects.

Responsibilities

• Deploy, benchmark, and optimize ML models for production on Google Cloud Platform.
• Integrate ML models into Java-based streaming applications.
• Design and execute performance, inference, and quality tests.
• Monitor production model performance and troubleshoot issues.
• Collaborate with ML researchers to evaluate models and improve deployment strategies.
• Drive deployment automation and ensure reliable production serving.

Requirements: Required Skills:

• 10+ years of IT experience with strong expertise in ML deployment and inference.
• Hands-on experience with Google Cloud Platform (Google Cloud Platform) for model deployment and serving.
• Strong knowledge of TensorFlow, PyTorch, JAX, or similar ML frameworks.
• Experience with ML model benchmarking, performance tuning, and quality testing.
• Ability to quickly learn and adapt to new technologies and evolving tech stacks.
• Strong problem-solving skills with an end-to-end ownership mindset.
• Understanding of distributed systems and debugging production environments.

Nice to Have: Exposure to Java/JVM-based applications.

• Experience with streaming data pipelines and hybrid cloud environments.
• Familiarity with deployment automation and production monitoring.